Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
DETAILED ACTION
Claims 1-20 are presented for examination.
This is a Non-Final Action.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102 of this title, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-5, 8, 11-15, and 18 rejected under 35 U.S.C. 103 as being unpatentable over Sungin et al. (KR20230079595 (English translation) in view of Chen et al. (US 10,969,233) and further in view of Rohlf et al. (US 8,650,220)
1. Sungin teaches, An apparatus for learning mixed data for approximate queries, comprising:
one or more processors; and memory for storing at least one program executed by the one or more processors (Page 3 – teaches “the DBMS 100 manages a database and provides an environment in which application programs can share and use the database”, Sungin), wherein the at least one program receives mixed data including relational data about information for identifying an object (Page 4 – teaches “the exact query module 600 manages the relational data 610”), and generates a mixed learning model that learns the relational data and the spatiotemporal data (Page 3 – teaches Fig 1 is a block diagram of a multi-model approximate query processing system…”; Page 4 – teaches The spatiotemporal module 500 creates a spatiotemporal model 510 – thus disclosing data distributions and creating models for relational and spatiotemporal data, Sungin) using multiple relational models and spatiotemporal models (Page 4 – teaches “A query result inference type machine learning (ML) module 300 learns a data distribution from raw data to create and manage a result inference model 310 . The data synopsis generation type machine learning (ML) module 400 creates a synopsis generation model 410 from raw data and generates a data synopsis 420 based on the synopsis generation model 410. The spatiotemporal module 500 creates a spatiotemporal model 510 from spatiotemporal data, and the exact query module 600 manages the relational data 610 .” – thus disclosing applying Sungin’s models at different spatial partitions (designated areas), Sungin).
Sungin does not explicitly teach,
…spatiotemporal data about a trajectory of the object moving in a target space, discretizes the relational data and the spatiotemporal data based on a level of detail that is preset for each designated area of the target space corresponding to the trajectory of the object.
However, Chen teaches,
…spatiotemporal data about a trajectory of the object moving in a target space (Col 6: lines 34-35 – teaches includes at time and the position of the vehicle at that time; Col 6: lines 55-56 – teaches a continuous trajectory is partitioned into a list of small sub-trajectories – thus disclosing spatiotemporal data representing a moving object’s trajectory in space, Chen).
It would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which said subject matter pertains to allow modify Sungin by incorporating Chen’s explicit trajectory modeling into Sungin’s spatiotemporal module to enhance the modeling of moving objects with the approximate query processing framework. Chen’s trajectory representation is directly applicable to Sungin’s spatiotemporal data processing and would have been recognized as a suitable implementation detail by a person of ordinary skill in the art seeking to process moving object data efficiently.
Rohlf teaches,
discretizes the relational data and the spatiotemporal data based on a level of detail that is preset for each designated area of the target space corresponding to the trajectory of the object (Abstract – teaches geospatial data can be spatially partitioned into geospatial volumes…; Col 4: lines 43-46 – teaches each of the discrete geospatial volumes can have … resolution and/or level of detail – thus disclosing hierarchical partitioning into areas/volumes defined by coordinate boundaries, Rohlf).
It would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which said subject matter pertains to apply Rohlf’s hierarchical spatial discretization and level of detail management techniques to Sungin’s spatiotemporal and relational data processing system in order to improve scalability, storage efficiency and query performance for large spatial datasets. Both references address efficient organization and processing of spatial data within database system and Rohlf’s partitioning scheme represents a predictable design choice for managing large-scale spatial information.
2. The combination of Sungin, Chen and Rohlf teach, The apparatus of claim 1, wherein the at least one program performs transformation into three-dimensional (3D) spatial data (Col 3: lines 6-7 – teaches “spatiotemporal data (data that has a location attribute in addition to timstamps), Chen) about time (Col 4: lines 32-34 – teaches each time series includes a plurality of data sets … includes a time and the position of the vehicle at that time, Chen), a space (Fig 2 – teaches a table having time and position data, Chen), and a trajectory of the spatiotemporal data (Col 6: lines 54-55 – teaches a continuous trajectory is partitioned into a list of small sub-trajectories, Chen).
3. The combination of Sungin, Chen and Rohlf teach, The apparatus of claim 2, wherein the spatiotemporal model (Page 4 - teaches the spatiotemporal module 500 creates a spatiotemporal model 510 from spatiotemporal data, Sungin)is configured with a three-layer structure (Col 5: lines 34-37 - teaches the hierarchical tree data structure can include a plurality of node levels configured in a parent-child relationship (i.e parent -> child -> grandchild (3 layer), Rohlf ) for learning the 3D spatial data for each layer (Col 6: lines 34-35 - teaches includes a time and the position of the vehicle at the time, Chen – thus the combination teaches - Since Rohlf partitions spatial data hierarchically into multiple levels, applying Chen’s spatiotemporal trajectory representation within those hierarchical levels would inherently result in learning 3D spatiotemporal data at each layer of the hierarchy).
4. The combination of Sungin, Chen and Rohlf teach, The apparatus of claim 1, wherein the at least one program sets levels of detail for each designated area (Abstract – teaches geospatial data can be spatially partitioned into geospatial volumes…; Col 4: lines 43-46 – teaches each of the discrete geospatial volumes can have … resolution and/or level of detail – thus disclosing hierarchical partitioning into areas/volumes defined by coordinate boundaries – thus disclosing hierarchical spatial partitioning into discreet geospatial volumes having defined resolution/LOD, further disclosing multiple hierarchical node level corresponding to different spatial resolutions, Rohlf)based on time during which the object is present in the designated area (Col 6: lines 34-35 - teaches includes a time and the position of the vehicle at the time; Col 6: lines 54-55 – teaches a continuous trajectory is partitioned into a list of small sub-trajectories – thus teaching determining spatial representation granularity (LOD) based on duration within a region is predictable implementation when combining Rohlf’s teaching of hierarchical spatial volumes with selectable level of details with Chen’s time-indexed spatial trajectories enabling determination of how long an object remains within a spatial region, under BRI, time spent within a spatial partition corresponds directly to presence duration in a designated area, Chen).
5. The combination of Sungin, Chen and Rohlf teach, The apparatus of claim 4, wherein the at least one program discretizes the relational data and the spatiotemporal data (Abstract - teaches geospatial data can be spatially partitioned into a plurality of discrete geospatial volumes – thus disclosing hierarchical subdivisions into multiple level, i.e., discretization into spatial partitions. Under BRI, discretizing trajectory data into spatial partitions constitutes discretizing spatiotemporal data) based on a probability expression (Page 4 - teaches learns a data distribution from raw data to create and manage a result inference model 310 – thus disclosing learning a data distribution and performing approximate query processing inherently involves probability expressions and probabilistic inference, Sungin )for checking the trajectory of the object moving in the designated area of the target space (Col 6: lines 34-35 - teaches includes a time and the position of the vehicle at the time; Col 6: lines 54-55 – teaches a continuous trajectory is partitioned into a list of small sub-trajectories, Chen – thus disclosing trajectory models as time-indexed spatial positions, wherein the trajectory modeling allos checking whether an object’s trajectory intersects or passes through a spatial region (designated area). Under BRI, evaluating trajectory segments against spatial partitions constitutes “checking the trajectory in a designated area”).
8. The combination of Sungin, Chen and Rohlf teach, The apparatus of claim 1, wherein the mixed learning model (Page 3 - teaches multi-model approximate query processing system which includes (query result inference ML model, Synopsis generation ML model, Spatiotemporal module and Exact query module, Sungin) infers (Page 4 - teaches leans a data distribution from raw data to create and manage a result inference model, Sungin) a trajectory of an object moving in the target space (Col 6: lines 34-35 - teaches includes a time and the position of the vehicle at the time; Col 6: lines 54-55 – teaches a continuous trajectory is partitioned into a list of small sub-trajectories, Chen) by receiving a query statement (Page 7 - receiving a query request from a approximate query processing coordinator, parsing the query in the query processing engine… - thus disclosing receing and parsing a query to invoke appropriate models, Sungin).
Claims 11-15 and 18 are similar to claims 1-5 and 8 hence rejected similarly.
Claims 9,10, 19 and 20 rejected under 35 U.S.C. 103 as being unpatentable over Sungin et al. (KR20230079595 (English translation) in view of Chen et al. (US 10,969,233) and Rohlf et al. (US 8,650,220) further in view of Zasadzinski et al. (US 2017/0372212)
All limitations of claim 8 are taught above.
9. The combination of Sungin, Chen and Rohlf teach, the spatiotemporal model (Page 4 – teaches the spatiotemporal module 500 creates a spatiotemporal model 510, Sungin).
The combination of Sungin, Chen and Rohlf do not explicitly teach, wherein a preset probabilistic circuits model is used for the relational model.
However, Zasadzinski teaches, wherein a preset probabilistic circuits model (Fig 2:204 - teaches the analyzer generates an AC for each component type based on the component models – thus disclosing generating AC from statistical models, Acs are probabilistic computational graphs encoding joint probability functions; Paragraph 31 – teaches the AC evaluator 120 may first search the evaluated circuit 120 to determine whether any Acs … have been pre-evaluated or computed offline and cached – thus teaching “preset”, Zasadzinski) is used for the relational model (Paragraph 69 – teaches the network representation 401 is depicted as a Bayesian network… - thus disclosing statistical models encoding dependencies among variables (i.e. relational probabilistic models); Claim 9 – teaches generate, using the subset of arithmetic circuits, a diagnosis model in accordance with dependencies among the first component – thus disclosing the AC are used to represent and evaluate relational dependencies among components, thereby satisfies use of the probabilistic circuit for a relational model, Zasadzinski).
It would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which said subject matter pertains to combine Sungin with Zasadznski because both are in the same field of endeavor, directed to probabilistic modeling and inference in structured computational systems. Zasadzinski teaches compiling probabilistic graphic models into arithmetic circuits to enable efficient probabilistic evaluation. Because Sungin employs model-based approximate query inference over structured data, Zasadzinski is reasonably pertinent to the problem of improving computational efficiency of probabilistic model evaluation
10. The combination of Sungin, Chen and Rohlf teach, The apparatus of claim 9, wherein the query statement is transformed (Page 3 - teaches approximate query coordinator 200 determines a optimized execution model by analyzing the requested query – thus disclosing parsing/analyzing a query and determining a model for execution; Page 3 - teaches approximate query coordinator 200 delivers table names and filter information, which are information necessary for inference, to a module corresponding to the optimized execution model - thus disclosing converting the query into structured input (table names + filer information_ passes to a model, Sungin) into a probability expression (Paragraph 37 - teaches the analyzer determines a multi-linear function that represents the component models. For example… the multi-linear function may be represented as following: f =… - thus disclosing representation statistical models as multi-linear polynomial probability functions prior to circuit constructions) for application to the probabilistic circuits model (Paragraph 32 - teaches the arithmetic circuit evaluator 120 evaluates the diagnosis model 111 by inputting the values … into the Acs … and performing the operations indicated by the operational nodes of the Acs – thus disclosing applying input values to an arithmetic circuit to perform probabilistic evaluation. This corresponds to applying a probability expression to the probabilistic circuit model).
Claim 19 is similar to claim 9 hence rejected similarly.
Claim 10 is similar to claim 20 hence rejected similarly.
Allowable Subject Matter
Claims 6, 7, 16 and 17 objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to AMRESH SINGH whose telephone number is (571)270-3560. The examiner can normally be reached Monday-Friday 8am-5pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Ann J. Lo can be reached at (571) 272-9767. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/AMRESH SINGH/Primary Examiner, Art Unit 2159